Video input rides on whatever video track the participant publishes. That can be their
camera or a screen share; the agent sees either the same way.
Realtime vision
Use a realtime model in the pipeline and turn onvision=True for the session, on the
zeroruntime.Room you invoke (pass the same Room to zeroruntime.serve() to apply it to
every caller). Frames from the
participant’s video are forwarded to the model alongside audio:
References
- Python
- Node JS
Examples
Vision (Realtime)
Stream video frames to a realtime agent.
Vision Hook
Hook into frames before they reach the model.